[DAGCombiner] Forward vector store to vector load with extract_subvector

Loading a smaller fixed vector type from a stored larger fixed vector type
can be substituted with an extract_subvector, provided the smaller type
entirely contained in the larger type, and an extract_element would be
legal for the given offset.

Author: joe-rivos

llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp

@@ -19913,6 +19913,27 @@ SDValue DAGCombiner::ForwardStoreValueToDirectLoad(LoadSDNode *LD) {
     }
   }
 
+  // Loading a smaller fixed vector type from a stored larger fixed vector type
+  // can be substituted with an extract_subvector, provided the smaller type
+  // entirely contained in the larger type, and an extract_element would be
+  // legal for the given offset.
+  if (TLI.isOperationLegalOrCustom(ISD::EXTRACT_SUBVECTOR, LDType) &&
+      LDType.isFixedLengthVector() && STType.isFixedLengthVector() &&
+      !ST->isTruncatingStore() && LD->getExtensionType() == ISD::NON_EXTLOAD &&
+      LDType.getVectorElementType() == STType.getVectorElementType() &&
+      (Offset * 8 + LDType.getFixedSizeInBits() <=
+       STType.getFixedSizeInBits()) &&
+      (Offset % LDType.getScalarStoreSize() == 0)) {
+    unsigned EltOffset = Offset / LDType.getScalarStoreSize();
+    // The extract index must be a multiple of the result's element count.
+    if (EltOffset % LDType.getVectorElementCount().getFixedValue() == 0) {
+      SDLoc DL(LD);
+      SDValue VecIdx = DAG.getVectorIdxConstant(EltOffset, DL);
+      Val = DAG.getNode(ISD::EXTRACT_SUBVECTOR, DL, LDType, Val, VecIdx);
+      return ReplaceLd(LD, Val, Chain);
+    }
+  }
+
   // TODO: Deal with nonzero offset.
   if (LD->getBasePtr().isUndef() || Offset != 0)
     return SDValue();

llvm/test/CodeGen/RISCV/forward-vec-store.ll

@@ -4,19 +4,19 @@
 define void @forward_store(<32 x half> %halves, ptr %p, ptr %p2, ptr %p3, ptr %p4) {
 ; CHECK-LABEL: forward_store:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    addi a4, a0, 16
-; CHECK-NEXT:    li a5, 32
-; CHECK-NEXT:    vsetvli zero, a5, e16, m4, ta, ma
+; CHECK-NEXT:    li a4, 32
+; CHECK-NEXT:    vsetivli zero, 8, e16, m2, ta, ma
+; CHECK-NEXT:    vslidedown.vi v16, v8, 8
+; CHECK-NEXT:    vsetivli zero, 8, e16, m4, ta, ma
+; CHECK-NEXT:    vslidedown.vi v12, v8, 16
+; CHECK-NEXT:    vsetvli zero, a4, e16, m4, ta, ma
 ; CHECK-NEXT:    vse16.v v8, (a0)
-; CHECK-NEXT:    addi a5, a0, 32
-; CHECK-NEXT:    addi a0, a0, 48
+; CHECK-NEXT:    vsetivli zero, 8, e16, m4, ta, ma
+; CHECK-NEXT:    vslidedown.vi v8, v8, 24
 ; CHECK-NEXT:    vsetivli zero, 8, e16, m1, ta, ma
-; CHECK-NEXT:    vle16.v v8, (a4)
-; CHECK-NEXT:    vle16.v v9, (a5)
-; CHECK-NEXT:    vle16.v v10, (a0)
-; CHECK-NEXT:    vse16.v v8, (a1)
-; CHECK-NEXT:    vse16.v v9, (a2)
-; CHECK-NEXT:    vse16.v v10, (a3)
+; CHECK-NEXT:    vse16.v v16, (a1)
+; CHECK-NEXT:    vse16.v v12, (a2)
+; CHECK-NEXT:    vse16.v v8, (a3)
 ; CHECK-NEXT:    ret
   store <32 x half> %halves, ptr %p, align 256
   %gep1 = getelementptr inbounds nuw i8, ptr %p, i32 16